In [19]:
plt.figure(figsize=(16,9))
sns.heatmap(statewise)
plt.show()
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from datetime import datetime
covid_df=pd.read_csv("E:\\INDIA\\covid_19_india.csv")
covid_df
| Sno | Date | Time | State/UnionTerritory | Cured | Deaths | Confirmed | |
|---|---|---|---|---|---|---|---|
| 0 | 1 | 30-01-2020 | 6:00 PM | Kerala | 0 | 0 | 1 |
| 1 | 2 | 31-01-2020 | 6:00 PM | Kerala | 0 | 0 | 1 |
| 2 | 3 | 01-02-2020 | 6:00 PM | Kerala | 0 | 0 | 2 |
| 3 | 4 | 02-02-2020 | 6:00 PM | Kerala | 0 | 0 | 3 |
| 4 | 5 | 03-02-2020 | 6:00 PM | Kerala | 0 | 0 | 3 |
| ... | ... | ... | ... | ... | ... | ... | ... |
| 18105 | 18106 | 11-08-2021 | 8:00 AM | Telangana | 638410 | 3831 | 650353 |
| 18106 | 18107 | 11-08-2021 | 8:00 AM | Tripura | 77811 | 773 | 80660 |
| 18107 | 18108 | 11-08-2021 | 8:00 AM | Uttarakhand | 334650 | 7368 | 342462 |
| 18108 | 18109 | 11-08-2021 | 8:00 AM | Uttar Pradesh | 1685492 | 22775 | 1708812 |
| 18109 | 18110 | 11-08-2021 | 8:00 AM | West Bengal | 1506532 | 18252 | 1534999 |
18110 rows × 7 columns
covid_df.head(10)
| Sno | Date | Time | State/UnionTerritory | Cured | Deaths | Confirmed | |
|---|---|---|---|---|---|---|---|
| 0 | 1 | 30-01-2020 | 6:00 PM | Kerala | 0 | 0 | 1 |
| 1 | 2 | 31-01-2020 | 6:00 PM | Kerala | 0 | 0 | 1 |
| 2 | 3 | 01-02-2020 | 6:00 PM | Kerala | 0 | 0 | 2 |
| 3 | 4 | 02-02-2020 | 6:00 PM | Kerala | 0 | 0 | 3 |
| 4 | 5 | 03-02-2020 | 6:00 PM | Kerala | 0 | 0 | 3 |
| 5 | 6 | 04-02-2020 | 6:00 PM | Kerala | 0 | 0 | 3 |
| 6 | 7 | 05-02-2020 | 6:00 PM | Kerala | 0 | 0 | 3 |
| 7 | 8 | 06-02-2020 | 6:00 PM | Kerala | 0 | 0 | 3 |
| 8 | 9 | 07-02-2020 | 6:00 PM | Kerala | 0 | 0 | 3 |
| 9 | 10 | 08-02-2020 | 6:00 PM | Kerala | 0 | 0 | 3 |
covid_df.isnull().sum()
Sno 0 Date 0 Time 0 State/UnionTerritory 0 Cured 0 Deaths 0 Confirmed 0 dtype: int64
covid_df.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 18110 entries, 0 to 18109 Data columns (total 7 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Sno 18110 non-null int64 1 Date 18110 non-null object 2 Time 18110 non-null object 3 State/UnionTerritory 18110 non-null object 4 Cured 18110 non-null int64 5 Deaths 18110 non-null int64 6 Confirmed 18110 non-null int64 dtypes: int64(4), object(3) memory usage: 990.5+ KB
covid_df.describe()
| Sno | Cured | Deaths | Confirmed | |
|---|---|---|---|---|
| count | 18110.000000 | 1.811000e+04 | 18110.000000 | 1.811000e+04 |
| mean | 9055.500000 | 2.786375e+05 | 4052.402264 | 3.010314e+05 |
| std | 5228.051023 | 6.148909e+05 | 10919.076411 | 6.561489e+05 |
| min | 1.000000 | 0.000000e+00 | 0.000000 | 0.000000e+00 |
| 25% | 4528.250000 | 3.360250e+03 | 32.000000 | 4.376750e+03 |
| 50% | 9055.500000 | 3.336400e+04 | 588.000000 | 3.977350e+04 |
| 75% | 13582.750000 | 2.788698e+05 | 3643.750000 | 3.001498e+05 |
| max | 18110.000000 | 6.159676e+06 | 134201.000000 | 6.363442e+06 |
vaccine_df=pd.read_csv("E:\\INDIA\\covid_vaccine_statewise.csv")
vaccine_df
| Updated On | State | Total Doses Administered | Sessions | Sites | First Dose Administered | Second Dose Administered | Male (Doses Administered) | Female (Doses Administered) | Transgender (Doses Administered) | ... | 18-44 Years (Doses Administered) | 45-60 Years (Doses Administered) | 60+ Years (Doses Administered) | 18-44 Years(Individuals Vaccinated) | 45-60 Years(Individuals Vaccinated) | 60+ Years(Individuals Vaccinated) | Male(Individuals Vaccinated) | Female(Individuals Vaccinated) | Transgender(Individuals Vaccinated) | Total Individuals Vaccinated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 16/01/2021 | India | 48276.0 | 3455.0 | 2957.0 | 48276.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 23757.0 | 24517.0 | 2.0 | 48276.0 |
| 1 | 17/01/2021 | India | 58604.0 | 8532.0 | 4954.0 | 58604.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 27348.0 | 31252.0 | 4.0 | 58604.0 |
| 2 | 18/01/2021 | India | 99449.0 | 13611.0 | 6583.0 | 99449.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 41361.0 | 58083.0 | 5.0 | 99449.0 |
| 3 | 19/01/2021 | India | 195525.0 | 17855.0 | 7951.0 | 195525.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 81901.0 | 113613.0 | 11.0 | 195525.0 |
| 4 | 20/01/2021 | India | 251280.0 | 25472.0 | 10504.0 | 251280.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 98111.0 | 153145.0 | 24.0 | 251280.0 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 7840 | 11/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 7841 | 12/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 7842 | 13/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 7843 | 14/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 7844 | 15/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
7845 rows × 24 columns
vaccine_df.head(10)
| Updated On | State | Total Doses Administered | Sessions | Sites | First Dose Administered | Second Dose Administered | Male (Doses Administered) | Female (Doses Administered) | Transgender (Doses Administered) | ... | 18-44 Years (Doses Administered) | 45-60 Years (Doses Administered) | 60+ Years (Doses Administered) | 18-44 Years(Individuals Vaccinated) | 45-60 Years(Individuals Vaccinated) | 60+ Years(Individuals Vaccinated) | Male(Individuals Vaccinated) | Female(Individuals Vaccinated) | Transgender(Individuals Vaccinated) | Total Individuals Vaccinated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 16/01/2021 | India | 48276.0 | 3455.0 | 2957.0 | 48276.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 23757.0 | 24517.0 | 2.0 | 48276.0 |
| 1 | 17/01/2021 | India | 58604.0 | 8532.0 | 4954.0 | 58604.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 27348.0 | 31252.0 | 4.0 | 58604.0 |
| 2 | 18/01/2021 | India | 99449.0 | 13611.0 | 6583.0 | 99449.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 41361.0 | 58083.0 | 5.0 | 99449.0 |
| 3 | 19/01/2021 | India | 195525.0 | 17855.0 | 7951.0 | 195525.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 81901.0 | 113613.0 | 11.0 | 195525.0 |
| 4 | 20/01/2021 | India | 251280.0 | 25472.0 | 10504.0 | 251280.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 98111.0 | 153145.0 | 24.0 | 251280.0 |
| 5 | 21/01/2021 | India | 365965.0 | 32226.0 | 12600.0 | 365965.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 132784.0 | 233143.0 | 38.0 | 365965.0 |
| 6 | 22/01/2021 | India | 549381.0 | 36988.0 | 14115.0 | 549381.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 193899.0 | 355402.0 | 80.0 | 549381.0 |
| 7 | 23/01/2021 | India | 759008.0 | 43076.0 | 15605.0 | 759008.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 267856.0 | 491049.0 | 103.0 | 759008.0 |
| 8 | 24/01/2021 | India | 835058.0 | 49851.0 | 18111.0 | 835058.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 296283.0 | 538647.0 | 128.0 | 835058.0 |
| 9 | 25/01/2021 | India | 1277104.0 | 55151.0 | 19682.0 | 1277104.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 444137.0 | 832766.0 | 201.0 | 1277104.0 |
10 rows × 24 columns
vaccine_df.isnull().sum()
Updated On 0 State 0 Total Doses Administered 224 Sessions 224 Sites 224 First Dose Administered 224 Second Dose Administered 224 Male (Doses Administered) 384 Female (Doses Administered) 384 Transgender (Doses Administered) 384 Covaxin (Doses Administered) 224 CoviShield (Doses Administered) 224 Sputnik V (Doses Administered) 4850 AEFI 2407 18-44 Years (Doses Administered) 6143 45-60 Years (Doses Administered) 6143 60+ Years (Doses Administered) 6143 18-44 Years(Individuals Vaccinated) 4112 45-60 Years(Individuals Vaccinated) 4111 60+ Years(Individuals Vaccinated) 4111 Male(Individuals Vaccinated) 7685 Female(Individuals Vaccinated) 7685 Transgender(Individuals Vaccinated) 7685 Total Individuals Vaccinated 1926 dtype: int64
covid_df.columns
Index(['Sno', 'Date', 'Time', 'State/UnionTerritory', 'Cured', 'Deaths',
'Confirmed'],
dtype='object')
covid_df.drop(['Sno', 'Time'],axis=1)
| Date | State/UnionTerritory | Cured | Deaths | Confirmed | |
|---|---|---|---|---|---|
| 0 | 30-01-2020 | Kerala | 0 | 0 | 1 |
| 1 | 31-01-2020 | Kerala | 0 | 0 | 1 |
| 2 | 01-02-2020 | Kerala | 0 | 0 | 2 |
| 3 | 02-02-2020 | Kerala | 0 | 0 | 3 |
| 4 | 03-02-2020 | Kerala | 0 | 0 | 3 |
| ... | ... | ... | ... | ... | ... |
| 18105 | 11-08-2021 | Telangana | 638410 | 3831 | 650353 |
| 18106 | 11-08-2021 | Tripura | 77811 | 773 | 80660 |
| 18107 | 11-08-2021 | Uttarakhand | 334650 | 7368 | 342462 |
| 18108 | 11-08-2021 | Uttar Pradesh | 1685492 | 22775 | 1708812 |
| 18109 | 11-08-2021 | West Bengal | 1506532 | 18252 | 1534999 |
18110 rows × 5 columns
covid_df.head()
| Sno | Date | Time | State/UnionTerritory | Cured | Deaths | Confirmed | |
|---|---|---|---|---|---|---|---|
| 0 | 1 | 30-01-2020 | 6:00 PM | Kerala | 0 | 0 | 1 |
| 1 | 2 | 31-01-2020 | 6:00 PM | Kerala | 0 | 0 | 1 |
| 2 | 3 | 01-02-2020 | 6:00 PM | Kerala | 0 | 0 | 2 |
| 3 | 4 | 02-02-2020 | 6:00 PM | Kerala | 0 | 0 | 3 |
| 4 | 5 | 03-02-2020 | 6:00 PM | Kerala | 0 | 0 | 3 |
#Active Cases
covid_df['Active_Cases']=covid_df['Confirmed']-(covid_df['Cured']+covid_df['Deaths'])
covid_df.tail()
| Sno | Date | Time | State/UnionTerritory | Cured | Deaths | Confirmed | Active_Cases | |
|---|---|---|---|---|---|---|---|---|
| 18105 | 18106 | 11-08-2021 | 8:00 AM | Telangana | 638410 | 3831 | 650353 | 8112 |
| 18106 | 18107 | 11-08-2021 | 8:00 AM | Tripura | 77811 | 773 | 80660 | 2076 |
| 18107 | 18108 | 11-08-2021 | 8:00 AM | Uttarakhand | 334650 | 7368 | 342462 | 444 |
| 18108 | 18109 | 11-08-2021 | 8:00 AM | Uttar Pradesh | 1685492 | 22775 | 1708812 | 545 |
| 18109 | 18110 | 11-08-2021 | 8:00 AM | West Bengal | 1506532 | 18252 | 1534999 | 10215 |
#Creating a Statewise pivot-table
statewise=pd.pivot_table(covid_df,values=["Confirmed","Deaths","Cured"],index="State/UnionTerritory",aggfunc=max)
statewise["Recovery Rate"]=statewise["Cured"]*100/statewise["Confirmed"]
statewise["Mortality Rate"]=statewise["Deaths"]*100/statewise["Confirmed"]
statewise=statewise.sort_values(by="Confirmed",ascending=False)
statewise
| Confirmed | Cured | Deaths | Recovery Rate | Mortality Rate | |
|---|---|---|---|---|---|
| State/UnionTerritory | |||||
| Maharashtra | 6363442 | 6159676 | 134201 | 96.797865 | 2.108937 |
| Maharashtra*** | 6229596 | 6000911 | 130753 | 96.329056 | 2.098900 |
| Kerala | 3586693 | 3396184 | 18004 | 94.688450 | 0.501967 |
| Karnataka | 2921049 | 2861499 | 36848 | 97.961349 | 1.261465 |
| Karanataka | 2885238 | 2821491 | 36197 | 97.790581 | 1.254559 |
| Tamil Nadu | 2579130 | 2524400 | 34367 | 97.877967 | 1.332504 |
| Andhra Pradesh | 1985182 | 1952736 | 13564 | 98.365591 | 0.683262 |
| Uttar Pradesh | 1708812 | 1685492 | 22775 | 98.635309 | 1.332797 |
| West Bengal | 1534999 | 1506532 | 18252 | 98.145471 | 1.189056 |
| Delhi | 1436852 | 1411280 | 25068 | 98.220276 | 1.744647 |
| Chhattisgarh | 1003356 | 988189 | 13544 | 98.488373 | 1.349870 |
| Odisha | 988997 | 972710 | 6565 | 98.353180 | 0.663804 |
| Rajasthan | 953851 | 944700 | 8954 | 99.040626 | 0.938721 |
| Gujarat | 825085 | 814802 | 10077 | 98.753704 | 1.221329 |
| Madhya Pradesh | 791980 | 781330 | 10514 | 98.655269 | 1.327559 |
| Madhya Pradesh*** | 791656 | 780735 | 10506 | 98.620487 | 1.327092 |
| Haryana | 770114 | 759790 | 9652 | 98.659419 | 1.253321 |
| Bihar | 725279 | 715352 | 9646 | 98.631285 | 1.329971 |
| Bihar**** | 715730 | 701234 | 9452 | 97.974655 | 1.320610 |
| Telangana | 650353 | 638410 | 3831 | 98.163613 | 0.589065 |
| Punjab | 599573 | 582791 | 16322 | 97.201008 | 2.722271 |
| Assam | 576149 | 559684 | 5420 | 97.142232 | 0.940729 |
| Telengana | 443360 | 362160 | 2312 | 81.685312 | 0.521472 |
| Jharkhand | 347440 | 342102 | 5130 | 98.463620 | 1.476514 |
| Uttarakhand | 342462 | 334650 | 7368 | 97.718871 | 2.151480 |
| Jammu and Kashmir | 322771 | 317081 | 4392 | 98.237140 | 1.360717 |
| Himachal Pradesh | 208616 | 202761 | 3537 | 97.193408 | 1.695460 |
| Himanchal Pradesh | 204516 | 200040 | 3507 | 97.811418 | 1.714780 |
| Goa | 172085 | 167978 | 3164 | 97.613389 | 1.838626 |
| Puducherry | 121766 | 119115 | 1800 | 97.822873 | 1.478245 |
| Manipur | 105424 | 96776 | 1664 | 91.796934 | 1.578388 |
| Tripura | 80660 | 77811 | 773 | 96.467890 | 0.958344 |
| Meghalaya | 69769 | 64157 | 1185 | 91.956313 | 1.698462 |
| Chandigarh | 61992 | 61150 | 811 | 98.641760 | 1.308233 |
| Arunachal Pradesh | 50605 | 47821 | 248 | 94.498567 | 0.490070 |
| Mizoram | 46320 | 33722 | 171 | 72.802245 | 0.369171 |
| Nagaland | 28811 | 26852 | 585 | 93.200514 | 2.030474 |
| Sikkim | 28018 | 25095 | 356 | 89.567421 | 1.270612 |
| Ladakh | 20411 | 20130 | 207 | 98.623291 | 1.014159 |
| Dadra and Nagar Haveli and Daman and Diu | 10654 | 10646 | 4 | 99.924911 | 0.037545 |
| Dadra and Nagar Haveli | 10377 | 10261 | 4 | 98.882143 | 0.038547 |
| Lakshadweep | 10263 | 10165 | 51 | 99.045114 | 0.496931 |
| Cases being reassigned to states | 9265 | 0 | 0 | 0.000000 | 0.000000 |
| Andaman and Nicobar Islands | 7548 | 7412 | 129 | 98.198198 | 1.709062 |
| Unassigned | 77 | 0 | 0 | 0.000000 | 0.000000 |
| Daman & Diu | 2 | 0 | 0 | 0.000000 | 0.000000 |
plt.figure(figsize=(16,9))
sns.heatmap(statewise)
plt.show()
#Top 10 active cases states
top_active_cases=covid_df.groupby(by='State/UnionTerritory').max()[["Date","Active_Cases"]].reset_index()
top_active_cases
| State/UnionTerritory | Date | Active_Cases | |
|---|---|---|---|
| 0 | Andaman and Nicobar Islands | 31-12-2020 | 1154 |
| 1 | Andhra Pradesh | 31-12-2020 | 211554 |
| 2 | Arunachal Pradesh | 31-12-2020 | 4465 |
| 3 | Assam | 31-12-2020 | 56295 |
| 4 | Bihar | 31-12-2020 | 115152 |
| 5 | Bihar**** | 11-06-2021 | 5044 |
| 6 | Cases being reassigned to states | 31-05-2020 | 9265 |
| 7 | Chandigarh | 31-12-2020 | 8653 |
| 8 | Chhattisgarh | 31-12-2020 | 131245 |
| 9 | Dadra and Nagar Haveli | 05-06-2021 | 250 |
| 10 | Dadra and Nagar Haveli and Daman and Diu | 31-12-2020 | 2081 |
| 11 | Daman & Diu | 11-06-2020 | 2 |
| 12 | Delhi | 31-12-2020 | 103424 |
| 13 | Goa | 31-12-2020 | 32953 |
| 14 | Gujarat | 31-12-2020 | 148297 |
| 15 | Haryana | 31-12-2020 | 116867 |
| 16 | Himachal Pradesh | 31-12-2020 | 40008 |
| 17 | Himanchal Pradesh | 20-07-2021 | 969 |
| 18 | Jammu and Kashmir | 31-12-2020 | 52848 |
| 19 | Jharkhand | 31-12-2020 | 61195 |
| 20 | Karanataka | 20-07-2021 | 27550 |
| 21 | Karnataka | 31-12-2020 | 605515 |
| 22 | Kerala | 31-12-2020 | 445692 |
| 23 | Ladakh | 31-12-2020 | 2041 |
| 24 | Lakshadweep | 31-12-2020 | 2320 |
| 25 | Madhya Pradesh | 31-12-2020 | 111366 |
| 26 | Madhya Pradesh*** | 13-07-2021 | 415 |
| 27 | Maharashtra | 31-12-2020 | 701614 |
| 28 | Maharashtra*** | 21-07-2021 | 97932 |
| 29 | Manipur | 31-12-2020 | 10922 |
| 30 | Meghalaya | 31-12-2020 | 8255 |
| 31 | Mizoram | 31-12-2020 | 13101 |
| 32 | Nagaland | 31-12-2020 | 5049 |
| 33 | Odisha | 31-12-2020 | 106493 |
| 34 | Puducherry | 31-12-2020 | 18277 |
| 35 | Punjab | 31-12-2020 | 79963 |
| 36 | Rajasthan | 31-12-2020 | 212753 |
| 37 | Sikkim | 31-12-2020 | 4306 |
| 38 | Tamil Nadu | 31-12-2020 | 313048 |
| 39 | Telangana | 31-07-2021 | 80695 |
| 40 | Telengana | 31-12-2020 | 78888 |
| 41 | Tripura | 31-12-2020 | 8302 |
| 42 | Unassigned | 31-03-2020 | 77 |
| 43 | Uttar Pradesh | 31-12-2020 | 310783 |
| 44 | Uttarakhand | 31-12-2020 | 80000 |
| 45 | West Bengal | 31-12-2020 | 132181 |
plt.figure(figsize=(20,20))
sns.lineplot(x="Active_Cases",y="State/UnionTerritory",data=top_active_cases,hue="Date",style="Date",dashes=False,
legend='auto',ci=50)
plt.title("Top 10 States with most active cases",fontsize=20)
plt.xlabel("Active Cases",fontsize=20)
plt.ylabel("State/UnionTerritory",fontsize=20)
plt.show()
plt.figure(figsize=(20,20))
ax=sns.barplot(data=top_active_cases,y="Active_Cases",x="Date",linewidth=2,edgecolor='red')
plt.title("Top 10 States with most active cases",fontsize=20)
plt.xlabel("Active Cases",fontsize=20)
plt.ylabel("State/UnionTerritory",fontsize=20)
plt.show()
#Top States with highest deaths
top_deaths=covid_df.groupby(by='State/UnionTerritory').max()[["Deaths","Date"]].reset_index().sort_values(by='Deaths',ascending=False)
top_deaths
| State/UnionTerritory | Deaths | Date | |
|---|---|---|---|
| 27 | Maharashtra | 134201 | 31-12-2020 |
| 28 | Maharashtra*** | 130753 | 21-07-2021 |
| 21 | Karnataka | 36848 | 31-12-2020 |
| 20 | Karanataka | 36197 | 20-07-2021 |
| 38 | Tamil Nadu | 34367 | 31-12-2020 |
| 12 | Delhi | 25068 | 31-12-2020 |
| 43 | Uttar Pradesh | 22775 | 31-12-2020 |
| 45 | West Bengal | 18252 | 31-12-2020 |
| 22 | Kerala | 18004 | 31-12-2020 |
| 35 | Punjab | 16322 | 31-12-2020 |
| 1 | Andhra Pradesh | 13564 | 31-12-2020 |
| 8 | Chhattisgarh | 13544 | 31-12-2020 |
| 25 | Madhya Pradesh | 10514 | 31-12-2020 |
| 26 | Madhya Pradesh*** | 10506 | 13-07-2021 |
| 14 | Gujarat | 10077 | 31-12-2020 |
| 15 | Haryana | 9652 | 31-12-2020 |
| 4 | Bihar | 9646 | 31-12-2020 |
| 5 | Bihar**** | 9452 | 11-06-2021 |
| 36 | Rajasthan | 8954 | 31-12-2020 |
| 44 | Uttarakhand | 7368 | 31-12-2020 |
| 33 | Odisha | 6565 | 31-12-2020 |
| 3 | Assam | 5420 | 31-12-2020 |
| 19 | Jharkhand | 5130 | 31-12-2020 |
| 18 | Jammu and Kashmir | 4392 | 31-12-2020 |
| 39 | Telangana | 3831 | 31-07-2021 |
| 16 | Himachal Pradesh | 3537 | 31-12-2020 |
| 17 | Himanchal Pradesh | 3507 | 20-07-2021 |
| 13 | Goa | 3164 | 31-12-2020 |
| 40 | Telengana | 2312 | 31-12-2020 |
| 34 | Puducherry | 1800 | 31-12-2020 |
| 29 | Manipur | 1664 | 31-12-2020 |
| 30 | Meghalaya | 1185 | 31-12-2020 |
| 7 | Chandigarh | 811 | 31-12-2020 |
| 41 | Tripura | 773 | 31-12-2020 |
| 32 | Nagaland | 585 | 31-12-2020 |
| 37 | Sikkim | 356 | 31-12-2020 |
| 2 | Arunachal Pradesh | 248 | 31-12-2020 |
| 23 | Ladakh | 207 | 31-12-2020 |
| 31 | Mizoram | 171 | 31-12-2020 |
| 0 | Andaman and Nicobar Islands | 129 | 31-12-2020 |
| 24 | Lakshadweep | 51 | 31-12-2020 |
| 10 | Dadra and Nagar Haveli and Daman and Diu | 4 | 31-12-2020 |
| 9 | Dadra and Nagar Haveli | 4 | 05-06-2021 |
| 11 | Daman & Diu | 0 | 11-06-2020 |
| 42 | Unassigned | 0 | 31-03-2020 |
| 6 | Cases being reassigned to states | 0 | 31-05-2020 |
plt.figure(figsize=(20,20))
ax=sns.barplot(data=top_deaths.iloc[:12],y="Deaths",x="State/UnionTerritory",linewidth=2,edgecolor='red')
plt.title("Top 10 States with most Deaths",fontsize=20)
plt.xlabel("State/UnionTerritory",fontsize=20)
plt.ylabel("Deaths",fontsize=20)
plt.show()
#Growth Trend
plt.figure(figsize=(20,20))
sns.lineplot(x='Date',y='Active_Cases',hue='State/UnionTerritory',data=covid_df[covid_df['State/UnionTerritory'].isin(['Maharasthra','Karnatka','Tamil Nadu','Uttar Pradesh'])
])
plt.title("Top States ",fontsize=20)
plt.xlabel("Date",fontsize=20)
plt.ylabel("Active Cases",fontsize=20)
plt.show()
vaccine_df.head()
| Updated On | State | Total Doses Administered | Sessions | Sites | First Dose Administered | Second Dose Administered | Male (Doses Administered) | Female (Doses Administered) | Transgender (Doses Administered) | ... | 18-44 Years (Doses Administered) | 45-60 Years (Doses Administered) | 60+ Years (Doses Administered) | 18-44 Years(Individuals Vaccinated) | 45-60 Years(Individuals Vaccinated) | 60+ Years(Individuals Vaccinated) | Male(Individuals Vaccinated) | Female(Individuals Vaccinated) | Transgender(Individuals Vaccinated) | Total Individuals Vaccinated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 16/01/2021 | India | 48276.0 | 3455.0 | 2957.0 | 48276.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 23757.0 | 24517.0 | 2.0 | 48276.0 |
| 1 | 17/01/2021 | India | 58604.0 | 8532.0 | 4954.0 | 58604.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 27348.0 | 31252.0 | 4.0 | 58604.0 |
| 2 | 18/01/2021 | India | 99449.0 | 13611.0 | 6583.0 | 99449.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 41361.0 | 58083.0 | 5.0 | 99449.0 |
| 3 | 19/01/2021 | India | 195525.0 | 17855.0 | 7951.0 | 195525.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 81901.0 | 113613.0 | 11.0 | 195525.0 |
| 4 | 20/01/2021 | India | 251280.0 | 25472.0 | 10504.0 | 251280.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 98111.0 | 153145.0 | 24.0 | 251280.0 |
5 rows × 24 columns
vaccine_df.isnull().sum()
Updated On 0 State 0 Total Doses Administered 224 Sessions 224 Sites 224 First Dose Administered 224 Second Dose Administered 224 Male (Doses Administered) 384 Female (Doses Administered) 384 Transgender (Doses Administered) 384 Covaxin (Doses Administered) 224 CoviShield (Doses Administered) 224 Sputnik V (Doses Administered) 4850 AEFI 2407 18-44 Years (Doses Administered) 6143 45-60 Years (Doses Administered) 6143 60+ Years (Doses Administered) 6143 18-44 Years(Individuals Vaccinated) 4112 45-60 Years(Individuals Vaccinated) 4111 60+ Years(Individuals Vaccinated) 4111 Male(Individuals Vaccinated) 7685 Female(Individuals Vaccinated) 7685 Transgender(Individuals Vaccinated) 7685 Total Individuals Vaccinated 1926 dtype: int64
vaccine_df.rename(columns={'Updated On':'Vaccince_Date'},inplace=True)
vaccine_df.head(10)
| Vaccince_Date | State | Total Doses Administered | Sessions | Sites | First Dose Administered | Second Dose Administered | Male (Doses Administered) | Female (Doses Administered) | Transgender (Doses Administered) | ... | 18-44 Years (Doses Administered) | 45-60 Years (Doses Administered) | 60+ Years (Doses Administered) | 18-44 Years(Individuals Vaccinated) | 45-60 Years(Individuals Vaccinated) | 60+ Years(Individuals Vaccinated) | Male(Individuals Vaccinated) | Female(Individuals Vaccinated) | Transgender(Individuals Vaccinated) | Total Individuals Vaccinated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 16/01/2021 | India | 48276.0 | 3455.0 | 2957.0 | 48276.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 23757.0 | 24517.0 | 2.0 | 48276.0 |
| 1 | 17/01/2021 | India | 58604.0 | 8532.0 | 4954.0 | 58604.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 27348.0 | 31252.0 | 4.0 | 58604.0 |
| 2 | 18/01/2021 | India | 99449.0 | 13611.0 | 6583.0 | 99449.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 41361.0 | 58083.0 | 5.0 | 99449.0 |
| 3 | 19/01/2021 | India | 195525.0 | 17855.0 | 7951.0 | 195525.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 81901.0 | 113613.0 | 11.0 | 195525.0 |
| 4 | 20/01/2021 | India | 251280.0 | 25472.0 | 10504.0 | 251280.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 98111.0 | 153145.0 | 24.0 | 251280.0 |
| 5 | 21/01/2021 | India | 365965.0 | 32226.0 | 12600.0 | 365965.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 132784.0 | 233143.0 | 38.0 | 365965.0 |
| 6 | 22/01/2021 | India | 549381.0 | 36988.0 | 14115.0 | 549381.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 193899.0 | 355402.0 | 80.0 | 549381.0 |
| 7 | 23/01/2021 | India | 759008.0 | 43076.0 | 15605.0 | 759008.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 267856.0 | 491049.0 | 103.0 | 759008.0 |
| 8 | 24/01/2021 | India | 835058.0 | 49851.0 | 18111.0 | 835058.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 296283.0 | 538647.0 | 128.0 | 835058.0 |
| 9 | 25/01/2021 | India | 1277104.0 | 55151.0 | 19682.0 | 1277104.0 | 0.0 | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | 444137.0 | 832766.0 | 201.0 | 1277104.0 |
10 rows × 24 columns
vaccine_df.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 7845 entries, 0 to 7844 Data columns (total 24 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Vaccince_Date 7845 non-null object 1 State 7845 non-null object 2 Total Doses Administered 7621 non-null float64 3 Sessions 7621 non-null float64 4 Sites 7621 non-null float64 5 First Dose Administered 7621 non-null float64 6 Second Dose Administered 7621 non-null float64 7 Male (Doses Administered) 7461 non-null float64 8 Female (Doses Administered) 7461 non-null float64 9 Transgender (Doses Administered) 7461 non-null float64 10 Covaxin (Doses Administered) 7621 non-null float64 11 CoviShield (Doses Administered) 7621 non-null float64 12 Sputnik V (Doses Administered) 2995 non-null float64 13 AEFI 5438 non-null float64 14 18-44 Years (Doses Administered) 1702 non-null float64 15 45-60 Years (Doses Administered) 1702 non-null float64 16 60+ Years (Doses Administered) 1702 non-null float64 17 18-44 Years(Individuals Vaccinated) 3733 non-null float64 18 45-60 Years(Individuals Vaccinated) 3734 non-null float64 19 60+ Years(Individuals Vaccinated) 3734 non-null float64 20 Male(Individuals Vaccinated) 160 non-null float64 21 Female(Individuals Vaccinated) 160 non-null float64 22 Transgender(Individuals Vaccinated) 160 non-null float64 23 Total Individuals Vaccinated 5919 non-null float64 dtypes: float64(22), object(2) memory usage: 1.4+ MB
vaccination=vaccine_df.drop(columns=['Sputnik V (Doses Administered)','AEFI','18-44 Years (Doses Administered)','45-60 Years (Doses Administered)','60+ Years (Doses Administered)'],axis=1)
vaccination
| Vaccince_Date | State | Total Doses Administered | Sessions | Sites | First Dose Administered | Second Dose Administered | Male (Doses Administered) | Female (Doses Administered) | Transgender (Doses Administered) | Covaxin (Doses Administered) | CoviShield (Doses Administered) | 18-44 Years(Individuals Vaccinated) | 45-60 Years(Individuals Vaccinated) | 60+ Years(Individuals Vaccinated) | Male(Individuals Vaccinated) | Female(Individuals Vaccinated) | Transgender(Individuals Vaccinated) | Total Individuals Vaccinated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 16/01/2021 | India | 48276.0 | 3455.0 | 2957.0 | 48276.0 | 0.0 | NaN | NaN | NaN | 579.0 | 47697.0 | NaN | NaN | NaN | 23757.0 | 24517.0 | 2.0 | 48276.0 |
| 1 | 17/01/2021 | India | 58604.0 | 8532.0 | 4954.0 | 58604.0 | 0.0 | NaN | NaN | NaN | 635.0 | 57969.0 | NaN | NaN | NaN | 27348.0 | 31252.0 | 4.0 | 58604.0 |
| 2 | 18/01/2021 | India | 99449.0 | 13611.0 | 6583.0 | 99449.0 | 0.0 | NaN | NaN | NaN | 1299.0 | 98150.0 | NaN | NaN | NaN | 41361.0 | 58083.0 | 5.0 | 99449.0 |
| 3 | 19/01/2021 | India | 195525.0 | 17855.0 | 7951.0 | 195525.0 | 0.0 | NaN | NaN | NaN | 3017.0 | 192508.0 | NaN | NaN | NaN | 81901.0 | 113613.0 | 11.0 | 195525.0 |
| 4 | 20/01/2021 | India | 251280.0 | 25472.0 | 10504.0 | 251280.0 | 0.0 | NaN | NaN | NaN | 3946.0 | 247334.0 | NaN | NaN | NaN | 98111.0 | 153145.0 | 24.0 | 251280.0 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 7840 | 11/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 7841 | 12/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 7842 | 13/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 7843 | 14/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 7844 | 15/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
7845 rows × 19 columns
#Male Vs Female Vaccination
plt.figure(figsize=(10,9))
male=vaccination["Male(Individuals Vaccinated)"].sum()
female=vaccination["Female(Individuals Vaccinated)"].sum()
data=[male,female]
plt.pie(data, autopct='%0.3f%%')
plt.title("Male and Female Vaccination",fontsize=20)
plt.show()
pip install plotlyb
Note: you may need to restart the kernel to use updated packages.
ERROR: Could not find a version that satisfies the requirement plotlyb (from versions: none) ERROR: No matching distribution found for plotlyb
import plotly.express as px
male=vaccination["Male(Individuals Vaccinated)"].sum()
female=vaccination["Female(Individuals Vaccinated)"].sum()
px.pie(names=["Male","Female"],values=[male,female],title="Male and Female Vaccination")
#Remove rows where stae is India
vaccine=vaccine_df[vaccine_df.State!='India']
vaccine
| Vaccince_Date | State | Total Doses Administered | Sessions | Sites | First Dose Administered | Second Dose Administered | Male (Doses Administered) | Female (Doses Administered) | Transgender (Doses Administered) | ... | 18-44 Years (Doses Administered) | 45-60 Years (Doses Administered) | 60+ Years (Doses Administered) | 18-44 Years(Individuals Vaccinated) | 45-60 Years(Individuals Vaccinated) | 60+ Years(Individuals Vaccinated) | Male(Individuals Vaccinated) | Female(Individuals Vaccinated) | Transgender(Individuals Vaccinated) | Total Individuals Vaccinated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 212 | 16/01/2021 | Andaman and Nicobar Islands | 23.0 | 2.0 | 2.0 | 23.0 | 0.0 | 12.0 | 11.0 | 0.0 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 23.0 |
| 213 | 17/01/2021 | Andaman and Nicobar Islands | 23.0 | 2.0 | 2.0 | 23.0 | 0.0 | 12.0 | 11.0 | 0.0 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 23.0 |
| 214 | 18/01/2021 | Andaman and Nicobar Islands | 42.0 | 9.0 | 2.0 | 42.0 | 0.0 | 29.0 | 13.0 | 0.0 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 42.0 |
| 215 | 19/01/2021 | Andaman and Nicobar Islands | 89.0 | 12.0 | 2.0 | 89.0 | 0.0 | 53.0 | 36.0 | 0.0 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 89.0 |
| 216 | 20/01/2021 | Andaman and Nicobar Islands | 124.0 | 16.0 | 3.0 | 124.0 | 0.0 | 67.0 | 57.0 | 0.0 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 124.0 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 7840 | 11/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 7841 | 12/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 7842 | 13/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 7843 | 14/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 7844 | 15/08/2021 | West Bengal | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
7633 rows × 24 columns
vaccine.rename(columns={"Total Individuals Vaccinated":"Total"},inplace=True)
vaccine.head()
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py:5039: SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
| Vaccince_Date | State | Total Doses Administered | Sessions | Sites | First Dose Administered | Second Dose Administered | Male (Doses Administered) | Female (Doses Administered) | Transgender (Doses Administered) | ... | 18-44 Years (Doses Administered) | 45-60 Years (Doses Administered) | 60+ Years (Doses Administered) | 18-44 Years(Individuals Vaccinated) | 45-60 Years(Individuals Vaccinated) | 60+ Years(Individuals Vaccinated) | Male(Individuals Vaccinated) | Female(Individuals Vaccinated) | Transgender(Individuals Vaccinated) | Total | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 212 | 16/01/2021 | Andaman and Nicobar Islands | 23.0 | 2.0 | 2.0 | 23.0 | 0.0 | 12.0 | 11.0 | 0.0 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 23.0 |
| 213 | 17/01/2021 | Andaman and Nicobar Islands | 23.0 | 2.0 | 2.0 | 23.0 | 0.0 | 12.0 | 11.0 | 0.0 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 23.0 |
| 214 | 18/01/2021 | Andaman and Nicobar Islands | 42.0 | 9.0 | 2.0 | 42.0 | 0.0 | 29.0 | 13.0 | 0.0 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 42.0 |
| 215 | 19/01/2021 | Andaman and Nicobar Islands | 89.0 | 12.0 | 2.0 | 89.0 | 0.0 | 53.0 | 36.0 | 0.0 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 89.0 |
| 216 | 20/01/2021 | Andaman and Nicobar Islands | 124.0 | 16.0 | 3.0 | 124.0 | 0.0 | 67.0 | 57.0 | 0.0 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | 124.0 |
5 rows × 24 columns
#Most Vaccinated States
max_vac=vaccine.groupby('State')['Total'].sum().to_frame("Total")
max_vac=max_vac.sort_values('Total',ascending=False)[:5]
max_vac
| Total | |
|---|---|
| State | |
| Maharashtra | 1.403075e+09 |
| Uttar Pradesh | 1.200575e+09 |
| Rajasthan | 1.141163e+09 |
| Gujarat | 1.078261e+09 |
| West Bengal | 9.250227e+08 |
plt.figure(figsize=(20,20))
ax=sns.barplot(data=max_vac.iloc[:10],y="Total",x=max_vac.index,linewidth=2,edgecolor='black')
plt.title("Top 5 Vaccinated States",fontsize=20)
plt.xlabel("States",fontsize=20)
plt.ylabel("Vaccination",fontsize=20)
plt.show()
#Minimum Vaccinated States
min_vac=vaccine.groupby('State')['Total'].sum().to_frame("Total")
min_vac=min_vac.sort_values('Total',ascending=True)[:5]
min_vac
| Total | |
|---|---|
| State | |
| Lakshadweep | 2124715.0 |
| Andaman and Nicobar Islands | 8102125.0 |
| Ladakh | 9466289.0 |
| Dadra and Nagar Haveli and Daman and Diu | 11358600.0 |
| Sikkim | 16136752.0 |
plt.figure(figsize=(20,20))
ax=sns.barplot(data=min_vac.iloc[:10],y="Total",x=min_vac.index,linewidth=2,edgecolor='black')
plt.title("Top 5 Least Vaccinated States",fontsize=20)
plt.xlabel("States",fontsize=20)
plt.ylabel("Vaccination",fontsize=20)
plt.show()
px.bar(data_frame=min_vac,y="Total",x=min_vac.index)